This presentation provides an overview of the Dell PowerEdge R730xd server performance results with Red Hat Ceph Storage. It covers the advantages of using Red Hat Ceph Storage on Dell servers with their proven hardware components that provide high scalability, enhanced ROI cost benefits, and support of unstructured data.
클라우드 컴퓨팅 기반 기술과 오픈스택(Kvm) 기반 Provisioning Ji-Woong Choi
TTA에 KVM 기반 프로비저닝 기술에 대한 데모 세션을 포함하는 세미나 관련 자료입니다. 클라우드환경으로 가고자 해서 Paas를 어떤 플랫폼위에 올린다면 그리고 가상화 환경이나 클라우드 환경으로 올린다면 어떤 환경으로 올릴것인가를 고민하여야 합니다.
그리고 이 hypervisor중에 cloud 환경에서 가장 주목받는 kvm을 기반으로 하는 두가지 가상화 클라우드 솔루션인 rhev와 openstack을 잠시 살펴볼 것입니다.
그리고 이러한 가상화 클라우드 환경에서 자동화 하는 솔류션을 어떻게 고려해야 하는가를 살펴보고, 그런 솔류션중에 하나인 아테나 피콕에 대해 살펴보겠습니다.
그리고 오픈스택환경하에서 구축해서 사용했던 사용기와 이를 자동화하기위해 개발자들이 사용했던 간단한 ansible provisioning 모습을 시연합니다.
This presentation provides an overview of the Dell PowerEdge R730xd server performance results with Red Hat Ceph Storage. It covers the advantages of using Red Hat Ceph Storage on Dell servers with their proven hardware components that provide high scalability, enhanced ROI cost benefits, and support of unstructured data.
클라우드 컴퓨팅 기반 기술과 오픈스택(Kvm) 기반 Provisioning Ji-Woong Choi
TTA에 KVM 기반 프로비저닝 기술에 대한 데모 세션을 포함하는 세미나 관련 자료입니다. 클라우드환경으로 가고자 해서 Paas를 어떤 플랫폼위에 올린다면 그리고 가상화 환경이나 클라우드 환경으로 올린다면 어떤 환경으로 올릴것인가를 고민하여야 합니다.
그리고 이 hypervisor중에 cloud 환경에서 가장 주목받는 kvm을 기반으로 하는 두가지 가상화 클라우드 솔루션인 rhev와 openstack을 잠시 살펴볼 것입니다.
그리고 이러한 가상화 클라우드 환경에서 자동화 하는 솔류션을 어떻게 고려해야 하는가를 살펴보고, 그런 솔류션중에 하나인 아테나 피콕에 대해 살펴보겠습니다.
그리고 오픈스택환경하에서 구축해서 사용했던 사용기와 이를 자동화하기위해 개발자들이 사용했던 간단한 ansible provisioning 모습을 시연합니다.
In the Cloud Native community, eBPF is gaining popularity, which can often be the best solution for solving different challenges with deep observability of system. Currently, eBPF is being embraced by major players.
Mydbops co-Founder, Kabilesh P.R (MySQL and Mongo Consultant) illustrates on debugging linux issues with eBPF. A brief about BPF & eBPF, BPF internals and the tools in actions for faster resolution.
TWS 8.6 new features (from the 2013 European Tour)Nico Chillemi
Tivoli Workload Scheduler version 8 release 6 represent really the release where an old era of scheduling changed. This presentation has been prepared in collabration with Flora Tramontano and the Rome Lab.
How to Troubleshoot OpenStack Without Losing SleepSadique Puthen
The complex architecture, design, and difficulties while troubleshooting amplifies the effort in debugging a problem with an OpenStack environment. This can give administrators and support associates sleepless nights if OpenStack native and supporting components are not configured properly and tuned for optimum performance, especially with large deployments that involve high availability and load balancing.
Kubernetes Clusters as a Service with GardenerQAware GmbH
Cloud Native Night November 2018, Munich: Talk by Dirk Marwinski (SAP).
Join our Meetup: www.meetup.com/cloud-native-muc
Abstract: There are many Open Source tools which help in creating and updating single Kubernetes clusters. Corporations usually require many clusters, depending on their size they may require hundreds or even thousands of clusters. However, the more clusters you need the harder it becomes to operate, monitor, manage, and keep all of them alive and up-to-date.
That is exactly what open source project “Gardener” focuses on. It is not just another provisioning tool, but it is rather designed to manage Kubernetes clusters as a service. It provides Kubernetes-conformant clusters on various cloud providers and the ability to maintain hundreds or thousands of them at scale. At SAP, we face this heterogeneous multi-cloud & on-premise challenge not only in our own platform, but also encounter the same demand at all our larger and smaller customers implementing Kubernetes & Cloud Native.
Inspired by the possibilities of Kubernetes and the ability to self-host, the foundation of Gardener is Kubernetes itself. While self-hosting, as in, to run Kubernetes components inside Kubernetes is a popular topic in the community, we apply a special pattern catering to the needs of operating a huge number of clusters with minimal total cost of ownership.
In this session Dirk will provide a comprehensive overview of Gardener, the underlying concepts, and talk about interesting implementation details. In addition there will be a hands-on sessions where attendants will be given free access to a Gardener instance and given the opportunity to dynamically create Kubernetes cluster and test them.
Rook turns distributed storage systems into self-managing, self-scaling, self-healing storage services. It automates the tasks of a storage administrator: deployment, bootstrapping, configuration, provisioning, scaling, upgrading, migration, disaster recovery, monitoring, and resource management.
Rook uses the power of the Kubernetes platform to deliver its services via a Kubernetes Operator for each storage provider.
Oleg Chunikhin, Co-Founder and CTO @ Kublr.com, will present an introduction to storage management on k8s using Rook and Ceph.
Linux kernel status in RISC-V (July 2018) presented at RISC-V Chennai workshop
https://content.riscv.org/wp-content/uploads/2018/07/0930-19.07.18-Atish-Patra-Western-Digital.pdf
Performance Schema is a powerful diagnostic instrument for:
- Query performance
- Complicated locking issues
- Memory leaks
- Resource usage
- Problematic behavior, caused by inappropriate settings
- More
It comes with hundreds of options which allow precisely tuning what to instrument. More than 100 consumers store collected data.
In this tutorial, we will try all the important instruments out. We will provide a test environment and a few typical problems which could be hardly solved without Performance Schema. You will not only learn how to collect and use this information but have experience with it.
Tutorial at Percona Live Austin 2019
ntroduced in Splunk 6.2, the Distributed Management Console helps Splunk Admins deal with the monitoring and health of their Splunk deployment. In Splunk 6.3, we built views for Splunk Index and Volume Usage, Forwarder Monitoring, Search Head Cluster Monitoring, Index Cluster Monitoring, and tools for visualizing your Splunk Topology. Leverage Splunk DMC and come see the forest -and- the trees in your Splunk deployment!
Ibm power systems e870 and e880 technical overview and introductionDiego Alberto Tamayo
This IBM® Redpaper™ publication is a comprehensive guide covering the IBM Power System E870 (9119-MME) and IBM Power System E880 (9119-MHE) servers that support IBM AIX®, IBM i, and Linux operating systems. The objecti
ve of this paper is to introduce the major innovative Power E870 and Power E880 offerings and their relevant functions:
In the Cloud Native community, eBPF is gaining popularity, which can often be the best solution for solving different challenges with deep observability of system. Currently, eBPF is being embraced by major players.
Mydbops co-Founder, Kabilesh P.R (MySQL and Mongo Consultant) illustrates on debugging linux issues with eBPF. A brief about BPF & eBPF, BPF internals and the tools in actions for faster resolution.
TWS 8.6 new features (from the 2013 European Tour)Nico Chillemi
Tivoli Workload Scheduler version 8 release 6 represent really the release where an old era of scheduling changed. This presentation has been prepared in collabration with Flora Tramontano and the Rome Lab.
How to Troubleshoot OpenStack Without Losing SleepSadique Puthen
The complex architecture, design, and difficulties while troubleshooting amplifies the effort in debugging a problem with an OpenStack environment. This can give administrators and support associates sleepless nights if OpenStack native and supporting components are not configured properly and tuned for optimum performance, especially with large deployments that involve high availability and load balancing.
Kubernetes Clusters as a Service with GardenerQAware GmbH
Cloud Native Night November 2018, Munich: Talk by Dirk Marwinski (SAP).
Join our Meetup: www.meetup.com/cloud-native-muc
Abstract: There are many Open Source tools which help in creating and updating single Kubernetes clusters. Corporations usually require many clusters, depending on their size they may require hundreds or even thousands of clusters. However, the more clusters you need the harder it becomes to operate, monitor, manage, and keep all of them alive and up-to-date.
That is exactly what open source project “Gardener” focuses on. It is not just another provisioning tool, but it is rather designed to manage Kubernetes clusters as a service. It provides Kubernetes-conformant clusters on various cloud providers and the ability to maintain hundreds or thousands of them at scale. At SAP, we face this heterogeneous multi-cloud & on-premise challenge not only in our own platform, but also encounter the same demand at all our larger and smaller customers implementing Kubernetes & Cloud Native.
Inspired by the possibilities of Kubernetes and the ability to self-host, the foundation of Gardener is Kubernetes itself. While self-hosting, as in, to run Kubernetes components inside Kubernetes is a popular topic in the community, we apply a special pattern catering to the needs of operating a huge number of clusters with minimal total cost of ownership.
In this session Dirk will provide a comprehensive overview of Gardener, the underlying concepts, and talk about interesting implementation details. In addition there will be a hands-on sessions where attendants will be given free access to a Gardener instance and given the opportunity to dynamically create Kubernetes cluster and test them.
Rook turns distributed storage systems into self-managing, self-scaling, self-healing storage services. It automates the tasks of a storage administrator: deployment, bootstrapping, configuration, provisioning, scaling, upgrading, migration, disaster recovery, monitoring, and resource management.
Rook uses the power of the Kubernetes platform to deliver its services via a Kubernetes Operator for each storage provider.
Oleg Chunikhin, Co-Founder and CTO @ Kublr.com, will present an introduction to storage management on k8s using Rook and Ceph.
Linux kernel status in RISC-V (July 2018) presented at RISC-V Chennai workshop
https://content.riscv.org/wp-content/uploads/2018/07/0930-19.07.18-Atish-Patra-Western-Digital.pdf
Performance Schema is a powerful diagnostic instrument for:
- Query performance
- Complicated locking issues
- Memory leaks
- Resource usage
- Problematic behavior, caused by inappropriate settings
- More
It comes with hundreds of options which allow precisely tuning what to instrument. More than 100 consumers store collected data.
In this tutorial, we will try all the important instruments out. We will provide a test environment and a few typical problems which could be hardly solved without Performance Schema. You will not only learn how to collect and use this information but have experience with it.
Tutorial at Percona Live Austin 2019
ntroduced in Splunk 6.2, the Distributed Management Console helps Splunk Admins deal with the monitoring and health of their Splunk deployment. In Splunk 6.3, we built views for Splunk Index and Volume Usage, Forwarder Monitoring, Search Head Cluster Monitoring, Index Cluster Monitoring, and tools for visualizing your Splunk Topology. Leverage Splunk DMC and come see the forest -and- the trees in your Splunk deployment!
Ibm power systems e870 and e880 technical overview and introductionDiego Alberto Tamayo
This IBM® Redpaper™ publication is a comprehensive guide covering the IBM Power System E870 (9119-MME) and IBM Power System E880 (9119-MHE) servers that support IBM AIX®, IBM i, and Linux operating systems. The objecti
ve of this paper is to introduce the major innovative Power E870 and Power E880 offerings and their relevant functions:
POWER8 the x86 Server Farm - IBM Business Partners use POWER8 to Lower Client...Paula Koziol
Discover ISV solutions built using Linux on IBM POWER8 that will lower your Total Cost of Ownership compared to alternative platform technologies. Gain a competitive advantage with these solutions that analyze more data faster and improve performance at a much lower cost. Linux on IBM POWER8 is the only infrastructure that provides both scale-out and scale-up capabilities that optimizes the efficiency of your workloads while reducing your costs, allowing you to handle any business challenge.
This presentation highlights several high value solutions we have developed with Independent Software Vendors (ISV) IBM Business Partners. Hear directly from our ISV partners on the partnership and the value we deliver to our joint customers.
Visit http://www.ibm.com/power for more information.
Also visit the IBM Systems ISVs YouTube video channel for additional ISV Solutions on IBM Power Systems: https://www.youtube.com/playlist?list=PLN0Az2aq_pjgJs-1fFX0fw4BMRy2GeaHC
Follow us at @IBMSystemsISVs (https://twitter.com/IBMSystemsISVs)
Learn about IBM Flex System p24L, p260 and p460 Compute Nodes. The IBM Flex System p260 and p460 Compute Nodes are servers based on IBM POWER architecture technologies. These compute nodes run in IBM Flex System Enterprise Chassis units to provide a high-density, high-performance compute node environment, using advanced processing technology. For more information on Pure Systems, visit http://ibm.co/18vDnp6.
Visit the official Scribd Channel of IBM India Smarter Computing at http://bit.ly/VwO86R to get access to more documents.
IBM POWER8 processor is the fastest available on the market, redefining Open Source performance. With this amazing processor, IBM and members of the OpenPower Foundation design innovative and cost-effective systems, delivering the infrastructure of choice for the most demanding workloads, in terms of throughput, scalability and reliability.
In this talk in english, Thibaud Besson will browse the key characteristics of Power Systems, why they are the most relevant for today's challenges, both from a technical and economical standpoint. Finally, we will review the possibilities you have to get your hands on one of these outstanding plateforms for your Open Source applications.
Learn about the IBM FlashSystem 720 and IBM FlashSystem 820. IBM FlashSystem 720 and IBM FlashSystem 820 storage systems deliver high performance, efficiency, and reliability for shared enterprise storage environments, helping clients around the world address performance issues with their most important applications and infrastructure. For more information on IBM Storage Systems, visit http://ibm.co/LIg7gk.
Visit the official Scribd Channel of IBM India Smarter Computing at http://bit.ly/VwO86R to get access to more documents.
[Café techno] - Ibm power7 - Les dernières annoncesGroupe D.FI
Annonces de la nouvelle technologie IBM Power7+
Depuis plus de 10 ans, les entreprises privilégient la technologie Power pour AIX, IBM i et Linux. Aujourd'hui, IBM élargit le leadership de ses plateformes Power en introduisant une évolution technologique avec l'architecture Power 7+.
D.FI vous invite à découvrir les nouvelles fonctionnalités Power 7+ qui peuvent vous aider à répondre aux exigences de votre informatique en vous offrant dynamiquement une plus grande efficacité, des fonctions d'analyse métier et centraliser les charges de travail.
Nouveautés :
Le Power 7+ est une puce octocoeurs gravée en 32 nm (contre 45 mn pour Power7) :
- Atouts : La fréquence d'horloge est dopée ;
- La taille du cache eDRAM est multipliée par 2,5.
De nouvelles fonctions : assistance matérielle à la compression de mémoire AME ("Active Memory Expansion“) et accélération cryptographiques.
Une évolution majeure permet désormais de créer jusqu'à 20 micro-partitions par coeurs Power7+
Featuring eX5, the 5th generation of enterprise X-Architecture® from IBM, and based on the new Intel® Xeon® processor 7500 series and Intel Xeon processor 6500 series, these new systems radically expand the capabilities of the x86 platform, breaking through memory bottlenecks with exceptional scalable performance and advanced reliability.
In this deck from the 2018 Swiss HPC Conference, Alexander Ruebensaal from ABC Systems AG presents: NVMe Takes It All, SCSI Has To Fall.
"NVMe has beome the main focus of storage developments when it comes to latency, bandwidth, IOPS. There is already a broad range of standard products available - server or network based."
Watch the video: https://insidehpc.com/2018/06/video-nvme-takes-scsi-fall/
Learn more: http://www.abcsystems.ch/
and
http://www.hpcadvisorycouncil.com/events/2018/swiss-workshop/agenda.php
Sign up for our insideHPC Newsletter: http://insidehpc.com/newsletter
High-Density Top-Loading Storage for Cloud Scale Applications Rebekah Rodriguez
In this webinar, we will discuss how high-capacity Top-Loading Storage systems are being used for enterprise and cloud scale applications and will identify the key features of the modular architecture for use in today’s software defined storage (SDS) environments. - https://www.brighttalk.com/webcast/17278/527798
With the HPE ProLiant DL325 Gen10 server, Hewlett Packard Enterprise is extending the worlds' most secure industry standard servers product families. This a secure and versatile single socket (1P) 1U AMD EPYC™ based platform offers an exceptional balance of processor, memory and I/O for virtualization and data intensive workloads. With up to 32 cores, up to 16 DIMMs, 2 TB memory capacity and support for up to 10 NVMe drives, this server delivers 2P performance with 1P economics.This datasheet includes features, port description, configuration guide and specification of this series.
To keep pace in a rapidly evolving marketplace, organizations must innovate faster than ever.
Companies today are making their services and data available through web APIs to internal and
external developers, creating higher value and new ecosystems. In this paper, we’ll discuss the
transformational effect APIs have had in the marketplace at large, the data they’re capable of
uncovering, and how companies are applying that data to create intelligent APIs to drive business.
Bitcoin: A Peer-to-Peer Electronic Cash System
Satoshi Nakamoto
satoshin@gmx.com
www.bitcoin.org
Abstract.
A purely peer-to-peer version of electronic cash would allow online
payments to be sent directly from one party to another without going through a
financial institution. Digital signatures provide part of the solution, but the main
benefits are lost if a trusted third party is still required to prevent double-spending.
We propose a solution to the double-spending problem using a peer-to-peer network.
The network timestamps transactions by hashing them into an ongoing chain of
hash-based proof-of-work, forming a record that cannot be changed without redoing
the proof-of-work. The longest chain not only serves as proof of the sequence of
events witnessed, but proof that it came from the largest pool of CPU power. As
long as a majority of CPU power is controlled by nodes that are not cooperating to
attack the network, they'll generate the longest chain and outpace attackers. The
network itself requires minimal structure. Messages are broadcast on a best effort
basis, and nodes can leave and rejoin the network at will, accepting the longest
proof-of-work chain as proof of what happened while they were gone.
Ibm systems servidor linux power8 de 1u ibm power system s821 lc un servidor ...Diego Alberto Tamayo
Características principales
●●●●Integre dos procesadores IBM® POWER8 en un formato 1U para cargas de trabajo con uso intensivo de computación●●●●Ofrezca densidad para implementaciones de virtualización, base de datos y computación de alto rendimiento (HPC)●●●●Despliegue sistemas de elevada versatilidad para gran diversidad de cargas de trabajo de servidores, que abarcan desde procesamientos de transacciones en línea (OLTP), hosting web y elevado rendimiento de big data.
Foreword
This paper is the result of a research project carried out by Labs
in EVRY Financial Services during the fall of 2015. The content of
this report is the result of a comprehensive study, featuring online
sources, literary works, as well as recordings of financial
conferences such as Consensus 2015 and Fintech Week 2015.
We aim to provide a comprehensive report detailing the
opportunities, challenges and key success factors for financial
institutions looking to leverage the opportunities presented by
blockchain technology.
We hope you enjoy this study and that it helps give you greater
understanding.
Investment Interest in Blockchain
• Blockchain has the potential to reduce infrastructure
cost by up to $20 billion a year.
• P2P money Transfer across international borders -
segment worth $500 B.
• Anderseen Horowitz ( VC firm) has invested over USD
$100 million into Blockchain technology
• All time Public/VC investment into Blockchain startups -
$894 million.
• Over 4000 active fintech startups in the NY arena and
investment in the sector tripling last year to $12 billion.
“Over the past two decades, the Internet has
revolutionized many aspects of business and
society... Yet the basic mechanics of how people
and organizations execute transactions… have
not been updated for the 21st century. Blockchain
could bring to those processes the openness and
efficiency we have come to expect
in the Internet Era.”
—Arvind Krishna
Senior VP, IBM Research
Blockchain rewires financial markets
How IBM can help
As one of the world’s leading research organizations, and one of the world’s top contributors to open source projects, IBM is committed to fostering the collaborative effort required to transform how people, governments and businesses transact and interact.
IBM provides clients the consulting and systems integration capabilities to design and rapidly adopt distributed ledgers, digital identity and blockchain solutions. IBM helps clients leverage the global scale, business domain expertise, and deep cloud integration experience required for the application
of these technologies. Learn more at ibm.com/blockchain
Ibm elastic storage server moderno sistema de almacenamiento definido por s...Diego Alberto Tamayo
Características principales
●●●●Aumente su productividad compartiendo datos entre distintas cargas de trabajo con un grupo de almacenamiento unificado para cargas de trabajo de archivos, objetos y Hadoop●●●●Aumente la escala y/o el r endimiento en bloques de construcción modulares con balanceo automatico de carga de trabajo●●●●Reconstruya discos con fallos con la tecnología Declustered Array redundante de discos independientes (RAID) basada en codificación del borrado desarrollada por IBM®●●●●Aloje múltiples inquilinos, ajuste la asignación de recursos y amplíe la escala a medida que evolucionen sus necesidades●●●●Utilice un sistema integrado construido sobre software para servidores IBM Power e IBM Specturm Scale●●●●Reduzca los tiempos de copia de seguridad y restauración utilizando un objetivo de copia de seguridad de alto rendimiento●●●●Elimine el aumento incontrolado de archivadores y los cuellos de botella habituales en los sistemas de almacenamiento conectados en red (NAS).
Ibm flash system a9000 una solución todo f lash altamente paralela para empre...Diego Alberto Tamayo
Características principales
●● ● ●Benefíciese del rendimiento de una
arquitectura altamente paralela y la
tecnología IBM® FlashCore combinadas
en un sistema innovador
●● ● ●Optimice la gestión económica del
almacenamiento con supresión de
patrones, deduplicación y compresión
●● ● ●Evite problemas de ‘vecinos ruidosos’
con funciones de calidad del servicio
(QoS) que admiten multipropiedad y
cargas de trabajo mixtas
●● ● ●Consiga un rendimiento extremo y
uniformes para satisfacer acuerdos de
nivel de servicio (SLA) para cargas de
trabajo imprevisibles y que hacen un uso
intensivo de los datos
●● ● ●Integre fácilmente con plataformas
VMware, OpenStack, Linux y Microsoft, y
prácticamente con cualquier
infraestructura existente
●● ● ●Simplifique la administración del
almacenamiento con la nueva e
innovadora interfaz de usuario.
IBM Object Storage and Software Defined Solutions - CleversafeDiego Alberto Tamayo
Digital Content Growth
• Continued growth in graphical content creation
• Multi-device and HD/4K/8K make it even more challenging to store and process data
• Time & location shifting: viewing on individual schedule
• Content life-cycle management provides a balance between cost & performance
while maintaining customer experience
• Meta data availability and access
• Digital disruption with Over The Top (OTT) digital only competitors - new business
models
• OTT viewing will grow from representing 3.4% of TV viewing hours in 2013 to
20.4% by 2017 in NA
• 63% stream on-demand media more than weekly
• Security and data protection are big issues.
• File sharing declines with legal on-demand options
• Connection speeds are increasing making new options possible
COLDCHAIN“Bringing high-quality vaccines and refrigerated medicine to patient...Diego Alberto Tamayo
Create a system to track the temperature of vaccine using Smart IoT Edge
devices, Smart IoT cloud Eco Systems, Blockchain and Smart Analytics from
manufacturing to storage to transport to consumption – Reduce Wastage and
Improve distribution and lower Inventory!
Highlights
●● ● ●Complete: combining compute, interconnect,
storage and system software
●● ● ●Modular and Extensible: match the
right combination of components and
configurations to meet your workload
●● ● ●Integrated: racked and tested in
IBM manufacturing to reduce time to
compute
Clients value IBM’s unique strengths in
business process transformation and
hybrid cloud technology
IBM’s approach to hybrid cloud enables clients
to put data to work for better decision making
and competitive advantage
IBM is ideally-positioned to satisfy end-to-end enterprise
requirements for the growing hybrid cloud: infrastructure,
application development, data, security, visibility and control
“Growth and comfort
do not co-exist”1
The world economy continues its transformation as
companies’ global operating footprints evolve based
on new opportunities, challenges and technology.
With growing political uncertainty, as well as new risks
and disruption ushered in by evolving technologies,
companies have to navigate an increasingly complex
international operating environment. This tenth edition
of IBM’s Global Location Trends report outlines the
latest trends in corporate location selection and how
today’s global dynamics influence where companies
locate, expand their businesses and create jobs
around the world.
Learning to trust artificial intelligence systems accountability, compliance ...Diego Alberto Tamayo
It’s not surprising that the
public’s imagination has
been ignited by Artificial
Intelligence since the term
was first coined in 1955.
In the ensuing 60 years,
we have been alternately
captivated by its promise,
wary of its potential for
abuse and frustrated by
its slow development.
The ecosystem equation collaboration in the connected economy @harvard biz @i...Diego Alberto Tamayo
IT infrastructure will play a vital role in enabling organizations to become
connected economy leaders. With an IT infrastructure designed for cognitive workloads, you can
act at the speed of thought. It accelerates technology breakthroughs through open architectures
that foster collaborative innovation. Finally, it works with your cloud platforms to extend the value
of your systems and data. Put it all together and instead of observing change unfold, you can seize
the opportunities created by the connected economy.
Device democracy -Saving the future of the #InternetOfThings @IBMIBV Diego Alberto Tamayo
Transforming businesses as
the Internet of Things expands
As a global electronics company, we understand the
issues facing the high-tech industry and the continuous
transformation required to thrive. Across the industry,
companies are turning their attention from smartphones and
tablets to a new generation of connected devices that will
transform not just the Electronics industry, but many others.
The IBM Global Electronics practice uniquely combines IBM
and partner services, hardware, software and research into
integrated solutions that can help you deliver innovation,
create differentiated customer experiences and optimize
your global operations.
Unlocking Productivity: Leveraging the Potential of Copilot in Microsoft 365, a presentation by Christoforos Vlachos, Senior Solutions Manager – Modern Workplace, Uni Systems
In the rapidly evolving landscape of technologies, XML continues to play a vital role in structuring, storing, and transporting data across diverse systems. The recent advancements in artificial intelligence (AI) present new methodologies for enhancing XML development workflows, introducing efficiency, automation, and intelligent capabilities. This presentation will outline the scope and perspective of utilizing AI in XML development. The potential benefits and the possible pitfalls will be highlighted, providing a balanced view of the subject.
We will explore the capabilities of AI in understanding XML markup languages and autonomously creating structured XML content. Additionally, we will examine the capacity of AI to enrich plain text with appropriate XML markup. Practical examples and methodological guidelines will be provided to elucidate how AI can be effectively prompted to interpret and generate accurate XML markup.
Further emphasis will be placed on the role of AI in developing XSLT, or schemas such as XSD and Schematron. We will address the techniques and strategies adopted to create prompts for generating code, explaining code, or refactoring the code, and the results achieved.
The discussion will extend to how AI can be used to transform XML content. In particular, the focus will be on the use of AI XPath extension functions in XSLT, Schematron, Schematron Quick Fixes, or for XML content refactoring.
The presentation aims to deliver a comprehensive overview of AI usage in XML development, providing attendees with the necessary knowledge to make informed decisions. Whether you’re at the early stages of adopting AI or considering integrating it in advanced XML development, this presentation will cover all levels of expertise.
By highlighting the potential advantages and challenges of integrating AI with XML development tools and languages, the presentation seeks to inspire thoughtful conversation around the future of XML development. We’ll not only delve into the technical aspects of AI-powered XML development but also discuss practical implications and possible future directions.
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...DanBrown980551
Do you want to learn how to model and simulate an electrical network from scratch in under an hour?
Then welcome to this PowSyBl workshop, hosted by Rte, the French Transmission System Operator (TSO)!
During the webinar, you will discover the PowSyBl ecosystem as well as handle and study an electrical network through an interactive Python notebook.
PowSyBl is an open source project hosted by LF Energy, which offers a comprehensive set of features for electrical grid modelling and simulation. Among other advanced features, PowSyBl provides:
- A fully editable and extendable library for grid component modelling;
- Visualization tools to display your network;
- Grid simulation tools, such as power flows, security analyses (with or without remedial actions) and sensitivity analyses;
The framework is mostly written in Java, with a Python binding so that Python developers can access PowSyBl functionalities as well.
What you will learn during the webinar:
- For beginners: discover PowSyBl's functionalities through a quick general presentation and the notebook, without needing any expert coding skills;
- For advanced developers: master the skills to efficiently apply PowSyBl functionalities to your real-world scenarios.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
GridMate - End to end testing is a critical piece to ensure quality and avoid...ThomasParaiso2
End to end testing is a critical piece to ensure quality and avoid regressions. In this session, we share our journey building an E2E testing pipeline for GridMate components (LWC and Aura) using Cypress, JSForce, FakerJS…
A tale of scale & speed: How the US Navy is enabling software delivery from l...sonjaschweigert1
Rapid and secure feature delivery is a goal across every application team and every branch of the DoD. The Navy’s DevSecOps platform, Party Barge, has achieved:
- Reduction in onboarding time from 5 weeks to 1 day
- Improved developer experience and productivity through actionable findings and reduction of false positives
- Maintenance of superior security standards and inherent policy enforcement with Authorization to Operate (ATO)
Development teams can ship efficiently and ensure applications are cyber ready for Navy Authorizing Officials (AOs). In this webinar, Sigma Defense and Anchore will give attendees a look behind the scenes and demo secure pipeline automation and security artifacts that speed up application ATO and time to production.
We will cover:
- How to remove silos in DevSecOps
- How to build efficient development pipeline roles and component templates
- How to deliver security artifacts that matter for ATO’s (SBOMs, vulnerability reports, and policy evidence)
- How to streamline operations with automated policy checks on container images
In his public lecture, Christian Timmerer provides insights into the fascinating history of video streaming, starting from its humble beginnings before YouTube to the groundbreaking technologies that now dominate platforms like Netflix and ORF ON. Timmerer also presents provocative contributions of his own that have significantly influenced the industry. He concludes by looking at future challenges and invites the audience to join in a discussion.
How to Get CNIC Information System with Paksim Ga.pptxdanishmna97
Pakdata Cf is a groundbreaking system designed to streamline and facilitate access to CNIC information. This innovative platform leverages advanced technology to provide users with efficient and secure access to their CNIC details.
Threats to mobile devices are more prevalent and increasing in scope and complexity. Users of mobile devices desire to take full advantage of the features
available on those devices, but many of the features provide convenience and capability but sacrifice security. This best practices guide outlines steps the users can take to better protect personal devices and information.
Maruthi Prithivirajan, Head of ASEAN & IN Solution Architecture, Neo4j
Get an inside look at the latest Neo4j innovations that enable relationship-driven intelligence at scale. Learn more about the newest cloud integrations and product enhancements that make Neo4j an essential choice for developers building apps with interconnected data and generative AI.
Monitoring Java Application Security with JDK Tools and JFR Events
Ibm power systems facts and features power 8
1. IBM Power Systems
1
IBM Power Systems™ servers and IBM BladeCenter® blade servers using IBM POWER7® and POWER7+®
processors are described in a separate Facts and Features report dated July 2013 (POB03022-USEN-28).
IBM Power Systems™ servers and IBM BladeCenter® blade servers using IBM POWER6® and POWER6+™
processors are described in a separate Facts and Features report dated April 2010 (POB03004-USEN-14).
Table of contents Page no.
IBM Power System S812LC and S822LC 4
IBM Power System S812L and S822L 5
IBM Power System S824L 6
IBM Power System S814, S822 and S824 7
IBM Power System E850 8
IBM Power System E870 9
IBM Power System E880 10
System S Class System Unit Details 11-12
Enterprise System, E850 System Unit and E870/E880 Node & Control Unit Details 13-14
Server I/O Drawers & Attachment 15
Physical Planning Characteristics 16
Warranty / Installation 17
System S Class Systems Software Support 18-19
Enterprise Systems Software Support 20
Performance Notes & More Information 21
IBM Power Systems Facts and Features:
Enterprise and Scale-out Systems with
POWER8™ Processor Technology
March 2016
2. IBM Power Systems
2
These notes apply to the description tables for the pages which follow:
Y Standard / Supported
Optional Optionally Available / Supported
N/A or - Not Available / Supported or Not Applicable
SOD Statement of General Direction announced
SLES SUSE Linux Enterprise Server
RHEL Red Hat Enterprise Linux
A CoD capabilities include: Capacity Upgrade on Demand option – permanent processor or memory
activation, Elastic Capacity on Demand – temporary processor or memory activation by the day, Utility
Capacity on Demand – temporary processor activation by the minute, and Trial Capacity on Demand.
B Elastic COD built-in to new Power E880 and includes a block of no-charge processor and memory days
a For IBM Manufacturing processes, one x8 PCIe slots must contain an Ethernet LAN available for client
use. .
b Use of expanded function storage backplane uses one PCIe slot in 2U servers and optionally uses a PCIe
slot in 4U servers
c Backplane provides dual high performance SAS controllers with 1.8 GB write cache expanded up to 7.2
GB with compression plus Easy Tier function plus two SAS ports for running an EXP24S drawer. 4-core
S814 does not support the attachment of an EXP24S to these ports
d Full benchmark results are located at ibm.com/systems/power/hardware/reports/system_perf.html
e Option is supported on IBM i only through VIOS.
f For simplicity in calculating maximum and consistently describing the max across the Scale-out Servers,
the 12-bay backplane is assumed. A higher max with the expanded function backplane is possible.
g USB-2 ports have limited client usage compared to USB-3 ports. Clients can use a USB-2 port to
communicate with a UPS
h 4-core Power S814 max capacity disk drive supported in system unit is 300 GB. 387GB SSD can be
used for higher capacity.
j Not available in PowerKVM environment
k Maximum memory for 4.1GHz S822 and S822L is 512GB unless water cooling is used.
m Except one predefined configuration (8-Core #EHJW) has only 32GB
n The 4.1GHz S822 requires water cooling to attain full rPerf values. With air cooling SMT8 is not
supported reducing the rPerf values about 8%. Also the memory maximum is 50% lower.
o Values for 64-, 96- and 128-core servers measured as multiples of 32-core partitions. Values for 96-, 144-
and 192-core servers measured as multiples of 48-core partitions. Values for 80-, 120-, and 160-core
servers measured as multiples of 40-core partitions.
p When no GPU installed
q Slot total shown are all available PCIe slots for client use. PCIe slots in the system unit used to attach a
PCIe Gen3 I/O drawer are excluded from total. Note one x8 PCIe slots must contain an Ethernet LAN
available for client use
s On Power S822, max size of 2-cores per IBM i partition. Multiple IBM i partitions supported. The
software tier is on P10.
For additional connectivity information, please reference the IBM Sales Manual for more information on I/O features and adapters.
3. IBM Power Systems
3
Why Power Systems?
Powerful forces—mobile, cloud and big data & analytics—are redefining how business gets
done. Leaders are leveraging these forces to deepen relationships with customers and partners,
drive new efficiencies and expand business models. IBM is the right partner to help you:
Leverage systems that optimize big data and analytics performance.
Power Systems are designed for big data—from operational to computational to business and
cognitive Watson solutions—are optimized for performance and can scale to support
demanding and growing workloads. Capitalize on the currency of data by finding business
insights faster and more efficiently. And gain the elasticity you need to handle the varying
analytics initiatives your business requires.
Realize the true potential of enterprise cloud.
Power Systems will help you deliver on the promise of cloud and take advantage of superior
cloud economics. With higher utilization and performance capabilities and the ability to scale
out and up, you can reap the benefits of improved economics associated with fewer scale-out
systems. Leveraging the robust security built into the foundation of Power Systems, you gain
the confidence you need to move more workloads to the cloud, capitalize on greater efficiencies
and do more.
Revolutionize the way IT is created and consumed.
POWER architecture is at the heart of the OpenPOWER Foundation, a community that’s taking
advantage of an open technology platform to help organizations create new opportunities and
design next-generation applications to drive business success. The first to adopt open server
technology, Power Systems help you more quickly and easily deliver a broader set of services
and incorporate new technologies using the same technology footprint
Follow us @IBMpowersystems
Learn more at www.ibm.com/power
4. IBM Power Systems
4
Power S812LC and Power S822LC
Product Line IBM Power S812LC IBM Power S822LC IBM Power S822LC
Machine type 8348-21C 8335-GTA 8335-GCA
System packaging 19" rack drawer (2U) 19" rack drawer (2U) 19" rack drawer (2U)
Microprocessor type 64-bit POWER8 64-bit POWER8 64-bit POWER8
# of processor sockets per server 1 2 2
Processor options
GHz (cores/socket) | # of cores
3.32 GHz (8) | 8
2.92 GHz (10) | 10
3.32 GHz (8) | 16
2.92 GHz (10) | 20
3.32GHz (8) | 16
2.92 GHz (10) | 20 .
EnergyScale N/A N/A N/A
Level 2 (L2) cache per core 512 KB 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB 8 MB
Level 4 (L4) cache per socket Up to 64 MB Up to 64 MB Up to 64 MB
System memory (minimum - maximum)
(1333 MHz DDR3)
128 GBm
– 1024 GB 128 GB – 1024 GB 32 GB – 1024 GB
Active Memory Expansion N/A N/A N/A
Reliability, availability, serviceability
Chipkill memory Y Y Y
Baseboard Management Controller Y Y Y
Hot-swappable disk/SSD bays Y(front only) N N
Processor Instruction Retry Y Y Y
Redundant hot-plug power Y N Yp
Redundant hot-plug cooling Redundant but not hot-plug Y Y
Node Add, Node Repair, Memory
Upgrade
N/A N/A N/A
Dual VIOS N/A N/A N/A
Capacity and expandability
Capacity on Demand (CoD) N/A N/A N/A
PowerVM PowerLinux Edition N/A N/A N/A
PowerKVM 3.1 Edition Optional N/A Optional
PowerVM Standard Edition N/A N/A N/A
PowerVM Enterprise Edition N/A N/A N/A
Max logical partitions/micro-partitions N/A N/A N/A
System unit PCIe Gen3 slots a
3 PCIe x8
1 PCIe x16
2 PCIe x8
3 PCIe x16
2 PCIe x8
3 PCIe x16
Max PCIe Gen3 I/O Drawer N/A N/A N/A
System unit disk/SSD bays 2 with mezz controller
12 more with PCIe adapter
2 SFF-4 2 SFF-4
Slimline DVD bay N/A N/A N/A
Maximum TB storage in system unit 84.0TB ( with 14x6TB ) 2.0 TB (with 2x 1TB disks) 2.0TB (with 2x 1TB disks )
Maximum EXP24S storage drawers N/A N/A N/A
Performance d
AIX rPerf
GHz (cores/socket): perf (# cores)
N/A
N/A
N/A
IBM i CPW
GHz (cores/socket): perf (# cores)
N/A N/A N/A
5. IBM Power Systems
5
Power S812L and S822L
Product Line IBM Power S812L IBM Power S822L
Machine type 8247-21L 8247-22L
System packaging 19" rack drawer (2U) 19" rack drawer (2U)
Microprocessor type 64-bit POWER8 64-bit POWER8
# of processor sockets per server 1 2
Processor options
GHz (cores/socket) | # of cores
3.42 GHz (10) | 10
3.02 GHz (12) | 12
3.42 GHz (10) | 20
3.02 GHz (12) | 24
4.15 GHz (8) | 16
EnergyScale Y Y
Level 2 (L2) cache per core 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB
Level 4 (L4) cache per socket Up to 128 MB Up to 128 MB
System memory (minimum –
maximum) (1600 MHz DDR3)
16 GB – 512 GB 32 GB -1024 GB k
Active Memory Expansion N/A N/A
Reliability, availability,
serviceability
Chipkill memory Y Y
Service processor Y Y
Hot-swappable disks/ SSD Y Y
Dynamic Processor Deallocation Y j
Y j
Processor Instruction Retry Y j
Y j
Alternate Processor Recovery Y j
Y j
Hot-plug concurrent maintenance
PCIe slots
Y j
Y j
Redundant hot-plug power Y Y
Redundant hot-plug cooling Y Y
Node Add, Node Repair, Memory
Upgrade
N/A N/A
Dual VIOS Optional j
Optional j
Capacity and expandability
Capacity on Demand (CoD) N/A N/A
PowerVM PowerLinux Edition Optional Optional
PowerKVM Edition Optional N/A
PowerVM Standard Edition N/A Optional
PowerVM Enterprise Edition N/A N/A
Max logical partitions/micro-partitions 240 480
System unit PCIe Gen3 low profile
slots a
4 PCIe x8
2 PCIe x16
5 PCIe x8
4 PCIe x16
Max PCIe Gen3 I/O Drawer ½ 1
Max PCIe Gen3 slots: system unit
+ PCIe I/O drawersq
10 (4 in system unit +
6 in I/O drawer) q
17 (5 in system unit +
12 in I/O drawer) q
System unit disk/SSD bays with
standard or split backplane
12 SFF-3 or
6+6 SFF-3
12 SFF-3 or
6+6 SFF-3
System unit disk/SSD bays with
expanded function backplane and
dual IOA with 7.2 GB write cache b, c
8 SFF-3 plus optional EXP24S
attachment for an additional 24
SFF-2 bays
8 SFF-3 plus 6 1.8-inch SSD bays
plus optional EXP24S attachment
for an additional 24 SFF-2 bays
Slimline DVD bay 1 1
Maximum TB storage in system unit 21.6 TB (with 12x 1.8 TB disks) 21.6 TB (with 12x 1.8 TB disks)
Maximum EXP24S storage drawers 28 28
Maximum EXP24S SAS bays 672 SFF-2 672 SFF-2
Max TB storage EXP24S 1,209 TB with 1.8 TB disks 1,209 TB with 1.8 TB disks
Performance d
AIX rPerf
GHz (cores/socket): perf (# cores)
N/A
N/A
IBM i CPW
GHz (cores/socket): perf (# cores)
N/A N/A
6. IBM Power Systems
6
Power S824L
Product Line IBM Power S824L IBM Power S824Lp
Machine type 8247-42L 8247-42L
System packaging 19" rack drawer (4U) 19" rack drawer (4U)
Microprocessor type 64-bit POWER8 64-bit POWER8
# of processor sockets per server 2 2
Processor options
GHz (cores/socket) | # of cores
3.42 GHz (10) | 20
3.02 GHz (12) | 24
4.15 GHz (8) | 8 or 16
3.52 GHz (12) | 24
EnergyScale Y Y
Level 2 (L2) cache per core 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB
Level 4 (L4) cache per socket Up to 128 MB Up to 128 MB
System memory (minimum -
maximum) (1600 MHz DDR3)
32 GB –2048 GB 32 GB –2048 GB
Active Memory Expansion N/A N/A
Reliability, availability,
serviceability
Chipkill memory Y Y
Service processor Y Y
Hot-swappable disks Y Y
Dynamic Processor Deallocation Y Y
Processor Instruction Retry Y Y
Alternate Processor Recovery N/A N/A
Hot-plug concurrent maintenance
PCIe slots
N/A N/A
Redundant hot-plug power Y Y
Redundant hot-plug cooling Y Y
Node Add, Node Repair, Memory
Upgrade
N/A N/A
Dual VIOS Optional Optional
Capacity and expandability
Capacity on Demand (CoD) N/A N/A
Active Memory Expansion N/A N/A
PowerVM PowerLinux Edition N/A Y
PowerKVM Edition N/A Optional
PowerVM Standard Edition N/A N/A
PowerVM Enterprise Edition N/A N/A
Max logical partitions/micro partitions N/A 480
System unit PCIe Gen3 full high slots
a
7 PCIe x8
4 PCIe x16
7 PCIe x8
4 PCIe x16
Max PCIe Gen3 I/O Drawers N/A 2
Max PCIe Gen3 slots: system unit
+ PCIe I/O drawers
7 in system unit 31 (7 in system unit +
24 in I/O drawer ) q
System unit disk bays with standard
backplane
12 SFF-3 12 SFF-3
System unit disk/SSD bays with
expanded function backplane and
dual IOA with 7.2GB write cache b, c
N/A 18 SFF-3 plus 8 1.8-inch SSD
bays plus optional EXP24S
attachment for an additional 24
SFF-2 bays
Slimline DVD bay 1 1
Maximum TB storage in system unit 14.4 TB (with 12 f
x 1.2TB disks) 21.6 TB (with 12 f
x 1.8 TB disks)
Maximum EXP24S storage drawers N/A 28
Maximum EXP24S SAS bays N/A 672 SFF-2
Maximum TB storage in EXP24S N/A 1,209 TB with 1.8 TB disks
Performance d
AIX rPerf
GHz (cores/socket): perf (# cores)
N/A N/A
IBM i CPW
GHz (cores/socket): perf (# cores)
N/A N/A
7. IBM Power Systems
7
Power S814, S822 and Power S824
Product Line IBM Power S814 IBM Power S822 IBM Power S824
Machine type 8286-41A 8284-22A 8286-42A
System packaging 19" rack drawer (4U) 19" rack drawer (2U) 19" rack drawer (4U)
Microprocessor type 64-bit POWER8 64-bit POWER8 64-bit POWER8
# of processor sockets per server 1 2 2
Processor options
GHz (cores/socket) | # of cores
3.02 GHz (4) | 4
3.02 GHz (6) | 6
3.72 GHz (8) | 8
3.02 GHz (4) | 4 .
3.89 GHz (6) | 6 or 12
3.42 GHz (10) | 10 or 20
4.15 GHz (8) | 8 or 16
3.89 GHz (6) | 6 or 12
4.15 GHz (8) | 8 or 16
3.52 GHz (12) | 24
.
EnergyScale Y Y Y
Level 2 (L2) cache per core 512 KB 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB 8 MB
Level 4 (L4) cache per socket Up to 128 MB Up to 128 MB Up to 128 MB
System memory (minimum - maximum)
(1600 MHz DDR3)
4-core: 16 GB – 64 GB
6/8-core: 16 GB – 1024 GB
32 GB – 512 GB (1 DCM)
32 GB – 1024 GB (2 DCM)
32 GB – 1 TB (1 DCM)
32 GB – 2 TB (2 DCM)
Active Memory Expansion Optional Optional Optional
Reliability, availability, serviceability
Chipkill memory Y Y Y
Service processor Y Y Y
Hot-swappable disks Y Y Y
Dynamic Processor Deallocation Y Y Y
Processor Instruction Retry Y Y Y
Alternate Processor Recovery Y Y Y
Hot-plug concurrent maintenance PCIe
slots
Y Y Y
Redundant hot-plug power Y Y Y
Redundant hot-plug cooling Y Y Y
Node Add, Node Repair, Memory
Upgrade
N/A N/A N/A
Dual VIOS Optional Optional Optional
Capacity and expandability
Capacity on Demand (CoD) N/A N/A N/A
PowerVM PowerLinux Edition N/A N/A N/A
PowerKVM Edition N/A N/A N/A
PowerVM Standard Edition Optional Optional Optional
PowerVM Enterprise Edition Optional Optional Optional
Max logical partitions/micro-partitions 160 400 480
System unit PCIe Gen3 full high slots a
5 PCIe x8
2 PCIe x16
5 PCIe x8
4 PCIe x16
7 PCIe x8
4 PCIe x16
Max PCIe Gen3 I/O Drawer 1 1 2
Max PCIe Gen3 slots: system unit
+ PCIe I/O drawersq
17 ( 5 in system unit +
12 in I/O drawer) q
17 ( 5 in system unit +
12 in I/O drawer ) q
31 ( 7 in system unit +
24 in I/O drawer) q
System unit disk/SSD bays with
standard or split backplane
4-core : 10 SFF-3 or 5+5 SFF-3
6/8-core : 12 SFF-3 or
6+6 SFF-3
12 SFF-3 or
6+6 SFF-3
12 SFF-3 or
6+6 SFF-3
System unit disk/SSD bays with
expanded function backplane and dual
IOA with 7.2GB write cache b, c
4-core: 10 SFF (no EXP24S)
6/8-core:18 SFF-3 plus optional
EXP24S attachment for an
additional 24 SFF-2 bays
8 SFF-3 plus 6 1.8-inch SSD bays plus
optional EXP24S attachment for an
additional 24 SFF-2 bays
18 SFF-3 plus 8 1.8-inch SSD
bays plus optional EXP24S
attachment for an additional 24
SFF-2 bays
Slimline DVD bay 1 1 1
Maximum TB storage in system unit 4-core : 3.0TB ( with 10x300GB )
6/8-core 32.4TB (with 18x 1.8TB disk)
21.6 TB (with 12x 1.8 TB disks) 35.4 TB (with 18x 1.8 TB disks
plus 8x 387 GB SSD )
Maximum EXP24S storage drawers 4-core: 0
6/8-core: 28
28 28
Maximum EXP24S SAS bays 6/8-core: 672 SFF-2 672 SFF-2 672 SFF-2
Max TB storage EXP24S f h
4-core: n/a
6/8-core: 1,209 TB with 1.8 TB
disks
1,209 TB with 1.8 TB disks 1,209 TB with 1.8 TB disks
Performance d
AIX rPerf
GHz (cores/socket): perf (# cores)
3.02 GHz (4) 66.9
3.02 GHz (6): 97.5
3.72 GHz (8): 143.9
3.02 GHz (4) : 66.9 (4)
3.89 GHz (6): 120.8 (6), 235.6 (12)
4.15 GHz (8) n
: 166.0 (8) ; 323.6 (16)
3.42 GHz (10): 177.8 (10) ; 346.7 (20)
3.89 GHz (6) : 120.8
4.15 GHz (8) : 166
3.89 GHz (12) : 235.6
4.15 GHz (16) : 323.6
3.52 GHz (24) : 421.9
IBM i CPW s
GHz (cores/socket): perf (# cores)
3.02 GHz (4): 39,500
3.02 GHz (6): 59,500
3.72 GHz (8): 85,500
3.89 GHz (6): 25,500 per 2 core LPAR
4.15 GHz (8):27,000 per 2 core LPAR
3.42 GHz (10): 23,000 per 2 core LPAR
3.89 GHz (12): 25,500 per 2 core LPAR
3.89 GHz (6) : 72,000
4.15 GHz (8) : 94,500
3.89 GHz (12) : 130,000
4.15 GHz (16) : 173,500
8. IBM Power Systems
8
4.15 GHz (16): 27,000 / 2c LPAR
3.42 GHz (20): 23,000 / 2c LPAR
3.52 GHz (24) : 230,500
Power E850
Product Line IBM Power E850
Machine type 8408-E8E
System packaging 19" rack drawer (4U)
Microprocessor type 64-bit POWER8
# of processor sockets per server 4
Processor options
GHz (cores/socket) | # of cores
3.7 GHz (8) | 32
3.35 GHz (10) | 40
3.3 GHz (12) | 48
Minimum number of cores activations 16 (3.7 GHz)
20 (3.35 GHz)
24 (3.02 GHz)
Energy scale Yes
Level 2 (L2) cache per core 512 KB
Level 3 (L3) cache per core 8 MB
Level 4 (L4) cache per socket Up to 128 MB
System memory: min / max / (min % active)
128 GB / 2 TB / (50%)
1600 MHz DDR3
128 GB / 2 TB / (50%)
SOD : max 4TB*
Active Memory Expansion Optional
Reliability, availability, serviceability
Chipkill memory Yes
Service processor Yes
Hot-swappable disks Yes
Phase redundant, integrated sparing voltage Yes
regulator modules for processors, memory and
I/O
Yes
Hot-swappable disks Yes
Dynamic Processor Deallocation Yes
Alternate Processor Recovery Yes
Hot plug PCIe slots
Yes
Active Memory Mirroring
Optional
Redundant hot-plug power Yes
Redundant fans for SAS controllers and drive
bays
Yes
Redundant, hot swappable fans for processor,
memory and PCIe slots
Yes
Dual VIOS
Optional
Capacity and expandability
Capacity on Demand (CoD) Yes˄
Power Integrated facility for Linux Optional
Max logical partitions/micropartitions 960 ( 20 per core)
System unit PCIe Gen3 full high slots a
3 PCIe x8
4-8 PCIe x16
(2 x16 slots per installed processor module)
Max PCIe Gen3 I/O Drawers 4
Max PCIe Gen3 slots 51
Slimline DVD bay 1
Maximum TB storage in system unit 15.9 TB
8 x 1.8TB disks +
4 x387 GB SSD
Maximum EXP24S storage drawers 64
Max in EXP24S (I/O) drawers 1536 | 2764 TB with 1.8 GB disk
Performance
AIX rPerf
GHz (cores/socket): perf (# cores)
3.02 GHz (12): 383.0(24), 565.0(36), 746.9(48)
3.35 GHz (10): 347.8(20), 513.0(30), 678.3(40)
3.72 GHz (8): 304.5(16), 449.2(24), 593.8(32)
9. IBM Power Systems
9
Statement of Direction. All statements regarding IBM's future direction and intent are subject to change or withdrawal without notice
Power E870
Product Line IBM Power E870 (1 node) IBM Power E870 (2 node)
Machine type 9119-MME 9119-MME
System packaging
19" rack drawer (7U)
One 5U system node & one 2U system
control unit
19" rack drawer (12U)
Two 5U system nodes & one 2U
system control unit
Microprocessor type 64-bit POWER8 64-bit POWER8
# of processor sockets per server 4 8 (4 per system node)
Processor options
GHz (cores/socket) | # of cores
4.02 GHz (8) | 32
4.19 GHz (10) | 40
4.02 GHz (8) | 64
4.19 GHz (10) | 80
Minimum number of core activations 8 8
Energy Scale Y Y
Level 2 (L2) cache per core 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB
Level 4 (L4) cache per socket Up to 128 MB Up to 128 MB
System memory: min / max / (min % active)
1600 MHz DDR3
256 GB / 8 TB / (50%) 512 GB / 16 TB / (50%)
Active Memory Expansion Optional Optional
Reliability, availability, serviceability
Chipkill memory Y Y
Service processor and clock Redundant with failover Redundant with failover
Hot-swappable disks N/A N/A
Dynamic Processor Deallocation Y Y
Processor Instruction Retry Y Y
Alternate Processor Recovery Y Y
Hot-plug PCIe slots Y Y
Blind-swap PCIe slots in system unit Y Y
Active Memory Mirroring Y Y
Redundant hot-plug power Y Y
Redundant hot-plug cooling Y Y
Dual VIOS Optional Optional
Capacity and expandability
Capacity on Demand (CoD) functions Y A
Y A
Power Enterprise Processor Pools Optional Optional
Power Integrated Facility for Linux Optional Optional
PowerVM Enterprise Edition Standard Standard
Max logical partitions/micro-partitions 800 (20 per core max) 1000
Max system node PCIe Gen3 x16 slots 8 16 (8 per node)
Max PCIe Gen3 I/O Drawers 4 8 (4 per node)
Max PCIe Gen3 slots: (all in PCIe Gen3 I/O drawers) 48k
96k
System Control Unit: media bay 1 optional DVD 1 optional DVD
Max disk storage in system node N/A N/A
Max EXP24S storage drawers 64 128
Max in EXP24S I/O drawers) disk drives │ Storage 1536 | 2764 TB with 1.8 GB disk 3072 | 5529 TB with 1.8 GB disk
Performance*
AIX rPerf
GHz (cores/socket): perf (# cores)
4.02 GHz (8): 674.5(32),
4.19 GHz (10): 856.0(40),
4.02 GHz (8): 1,349.0(64) o
4.19 GHz (10): 1,711.9(80) o
IBM i CPW
GHz (cores/socket): perf (# cores)
4.02 GHz (8): 359,000(32),
4.19 GHz (10): 460,000(40),
4.02 GHz (8): 711,000(64) o
4.19 GHz (10): 911,000(80) o
10. IBM Power Systems
10
Power E880 (3-node option also available, but not shown to save space)
Product Line IBM Power E880
(1 node)
IBM Power E880
(2 node)
IBM Power E880
(4 node )
Machine type 9119-MHE 9119-MHE 9119-MHE
System packaging
19" rack drawer (7U)
One 5U system node & one 2U
system control unit
19" rack drawer (12U)
Two 5U system nodes & one
2U system control unit
19" rack drawer (22U)
Four 5U system nodes & one 2U
system control unit
Microprocessor type 64-bit POWER8 64-bit POWER8 64-bit POWER8
# of processor sockets per server 4 8 (4 per system node) 16 (4 per system node)
Processor options
GHz (cores/socket) | # of cores
4.35 GHz (8) | 32
4.02 GHz (12) | 48
4.35 GHz (8) | 64
4.02 GHz (12) | 96
4.35 GHz (8) | 128
4.02 GHz (12) | 192
Minimum number cores active 8 8 8
Energy Scale Y Y Y
Level 2 (L2) cache per core 512 KB 512 KB 512 KB
Level 3 (L3) cache per core 8 MB 8 MB 8 MB
Level 4 (L4) cache per socket Up to 128 MB Up to 128 MB Up to 128 MB
System memory: min / max / (min % active)
1600 MHz DDR3
256 GB / 8 TB / (50%) 512 GB / 16 TB / (50%) 1 TB / 32 TB / (50%)
Active Memory Expansion Optional Optional Optional
Reliability, availability, serviceability
Chipkill memory Y Y Y
Service processor and clock Redundant with failover Redundant with failover Redundant with failover
Hot-swappable disks N/A N/A N/A
Dynamic Processor Deallocation Y Y Y
Processor Instruction Retry Y Y Y
Alternate Processor Recovery Y Y Y
Hot-plug PCIe slots Y Y Y
Blind-swap PCIe slots in system unit Y Y Y
Blind-swap PCIe slots in PCIe I/O drawer Y Y Y
Active Memory Mirroring Y Y Y
Redundant hot-plug power Y Y Y
Redundant hot-plug cooling Y Y Y
Dual VIOS Optional Optional Optional
Capacity and expandability
Capacity on Demand (CoD) functions Y A, B
Y A,B
Y A,B
Power Enterprise Processor Pools Optional Optional Optional
Power Integrated Facility for Linux Optional Optional Optional
PowerVM Enterprise Edition Standard Standard Standard
Max logical partitions/micro-partitions 960 (20 per core max) 1000 1000
Max system node PCIe Gen3 x16 slots 8 16 (8 per enclosure) 32 (8 per enclosure)
Max PCIe Gen3 I/O Drawers 4 8 (4 per node) 16 (4 per node)
Max PCIe Gen3 slots (all PCIe I/O drawers) 48 96 192
System Control Unit: media bay 1 optional DVD 1 optional DVD 1 optional DVD
Max disk storage in system unit N/A N/A N/A
Max EXP24S storage drawers 64 128 168
Max in EXP24S I/O drawers: disk drives │
Storage
1536 | 2764 TB with 1.8 GB
disk
4032 | 7257 TB with 1.8 GB
disk
4032 | 7257 TB with 1.8 GB
disk
Performance* u
rPerf
GHz (cores/socket): perf (# cores)
4.35 GHz (8): 716.3(32),
4.19 GHz (10) : 856.0 (40)
4.0 GHz (12) : 976.4 (48)
4.35 GHz (8): 1,432.5(64) o
4.19 GHz (10) : 1,711.9 (80) o
4.0 GHz (12) : 1952.9(96)
4.35 GHz (8): 2,865 (128) o
4.19 GHz (10) : 3,424.0 (160) o
4.0 GHz (12): 3905.8 (192)
IBM i CPW
GHz (cores/socket): perf (# cores)
4.35 GHz (8): 381,000(32)
4.19 GHz (10) : 460,000 (40)
4.02 GHz (12): 518,000(48)
4.35 GHz (8): 755,000(64) o
4.19 GHz (10) : 911,000 (80)
4.02 GHz (12): 1,034,000(96)
4.35 GHz (8): 1,523,000 (128) o
4.19 GHz (10) : 1,813,000 (160)
4.02 GHz (12): 2,069,000 (192)
Note: A 3-node column is not shown above to save space and allow a larger font to be used. 4.35GHz 3-node 96-core rPerf = 2,148.8 o
and
CPW = 1,144,000 o
4.19GHz 3-node 120-core rPerf = 2,568.0 o
and CPW = 1,362,000 o
4.02GHz 3-node 144-core rPerf = ,2,929.3 o
and CPW = 1,551,000 o
11. IBM Power Systems
11
System Unit Details (Power Systems S LC Class Servers)
System Unit Details Power S812LC Power S822LC
POWER8 SCM sockets 1 2
Number of SCMs 1 2
Max memory DIMM slots 32 32 (8 riser slots)
Max sustained memory
bandwidth to L4 cache from
SCM
115 GB/sec 115 GB/sec per socket,
230 GB/sec per system
Max peak memory bandwidth to
DIMMs from L4 cache
170 GB/sec 170 GB/sec per socket,
340 GB/sec per system
Integrated ports
System/serial (RJ45) 0 0
USB-3 3
(1 front & 2 rear)
2
(1 front * & 1 rear)
VGA 1 1
RJ45 for BMC and IMPI 1 (10/100 MbE) 1 (1GbE)
DB9 for BMC and IMPI 1 1
USB-1 1
Not enabled for client
1 internal
Not enabled for client
Ethernet for general use N/A N/A
HMC ports N/A (BMC used) N/A (BMC used)
PCIe Ethernet adapter optional 1 required a
SATA bays in system unit
2.5-inch (SFF) only N/A 2 SFF-4
3.5-inch (LFF) or SFF 14 0
Media bays
DVD-RAM slimline N/A N/A
HH for tape N/A N/A
SATA storage controllers for
disk/SSD
Y Y
Base backplane Y, mezz card Y, integrated
Split backplane Optional ** N/A
RAID adapter Optional *** N/A
Hybrid RAID function Optional *** N/A
Optional EXP24S ports N/A N/A
PCIe Gen3 adapter slots 4 5
PCIe x8 3 2
PCIe x16 1 3
Max PCIe bus speed (GHz) 8.0 (Gen3) 8.0 (Gen3)
Max I/O bandwidth* 64 GB/sec 128 GB/sec
Service indicator LEDs Y Y
* front USB-3 port run at USB-2 bandwidth
** Split is 2 bays in rear tray run by integrated mezzanine card and 12 bays in front run by PCIe adapter
*** RAID and hybrid RAID on the 12 bays in the front run by a PCIe adapter
12. IBM Power Systems
12
System Unit Details (Power Systems S Class Servers)
System Unit Details Power S812L
Power S822
Power S822L
Power S814 Power S824 Power S824L
POWER8 DCM sockets 1 2 1 2 2
Number of DCMs 1
1 or 2 for S822
2 for S822L
1 1 or 2 1p
or 2
Max memory DIMM card
slots
8 16 (with 2 DCM) 4-core: 4 usable
6/8-core: 8
16 (with 2 DCM)
16
Max sustained memory
bandwidth to L4 cache from
DCM
192 GB/sec 384 GB/sec 4-core: 96 GB/sec
6/8-core: 192 GB/sec
384 GB/sec (with 2
DCM) 384 GB/sec
Max peak memory bandwidth
to DIMMs from L4 cache
410 GB/sec 820 GB/sec 4-core: 205 GB/sec
6/8-core: 410 GB/sec
820 GB/sec (with 2
DCM)
820 GB/sec
Integrated ports
System/serial (RJ45) 1 1 1 1 1
USB-2 ports g
2 2 2 2 2
USB-3 ports 4 (2 front & 2 rear) 2 (2 front & 0 rear) 4 (2 front & 2 rear) 4 (2 front & 2 rear) 4 (2 front & 2 rear)
HMC ports (RJ45) 2 2 2 2 2
Ethernet adapter ports a 4x 1 Gb or
2x 10/1 Gb
4x 1 Gb or
2x 10/1 Gb
4x 1 Gb or
2x 10/1 Gb
4x 1 Gb or
2x 10/1 Gb
2 1 Gb
SAS bays in system unit
2.5-inch (disk/SSD) 12 or 8 SFF-3 12 or 8 SFF-3 4-core: 10 usable
6/8-core: 12 or 18
SFF-3
12 or 18 SFF-3
12 SFF-3 or
18 SFF-3p
1.8-inch (SSD) 0 0 or 6 0 0 or 8 0 or 8p
Media bays
DVD-RAM slimline 1 1 1 1 1
HH for tape N/A N/A N/A N/A N/A
Integrated SAS storage
controllers for disk/SSD/DVD
Y Y Y Y Y
Base backplane 1 (zero write cache) 1 (zero write cache) 1 (zero write cache) 1 (zero write cache) 1 (zero write cache)
Split backplane 2 (zero write cache) 2 (zero write cache) 2 (zero write cache) 2 (zero write cache) 2 (zero write cache)P
Expanded function
backplane b, c
Dual IOA (7.2 GB
write cache) b, c
Dual IOA (7.2 GB
write cache) b, c
Dual IOA (7.2 GB write
cache) b, c
Dual IOA (7.2 GB
write cache) b, c
Dual IOA (7.2 GB
write cache) b, c, p
Easy Tier function Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplanep
Optional EXP24S ports
Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplane
Y with expanded
function backplanep
PCIe Gen3 adapter slots 6 9 (w/ 2 DCM) 7 11 (w/ 2 DCM) 11
PCIe x8 4 5 5 7 7
PCIe x16 2 4 2 4 4
Max PCIe bus speed (GHz) 8.0 (Gen3) 8.0 (Gen3) 8.0 (Gen3) 8.0 (Gen3) 8.0(Gen3)
Max I/O bandwidth 96 GB/sec 96 GB/sec per DCM 96 GB/sec 96 GB/sec per DCM 192 GB/sec
Service indicator LEDs Y Y Y Y Y
Storage backplane notes: Integrated SAS controllers are based on latest IBM patented SAS RAID adapter technology. All backplane options
offer RAID 0, 1, 5, 6, 10 capabilities plus hot spare capability. Write cache is mirrored for protection and physically is two 1.8 GB DRAM caches
offering up to 7.2 GB effective capacity with compression. One optional EXP24S storage drawer attachment is to two SAS ports on rear of
server which is available with the expanded function backplane. The EXP24S is external to the system unit taking 2U rack space and attached
via SAS cables and provides 24 SSF-2 SAS bays for disk or for SSD.
13. IBM Power Systems
13
System Unit Details (Power Enterprise Servers)
Power E850
System Unit Details With 2 processor modules With 3 processor modules With 4 processor modules
POWER8 sockets 4 (2 filled) 4 (3 filled) 4 (4 filled)
Number of processor modules 2 3 4
Memory DIMM slots 16 24 32
Max sustained memory bandwidth
to L4 cache from DCM
384 GB/sec 576 GB/sec 768 GB/sec
Max peak memory bandwidth to
DIMMs from L4 cache
820 GB/sec 1230 GB/sec 1640 GB/sec
Integrated ports
System/serial (RJ45) 1 1 1
USB-2 ports g
2 2 2
USB-3 ports 4 (2 front & 2 rear) 4 (2 front & 2 rear) 4 (2 front & 2 rear)
HMC ports (RJ45) 2 2 2
Ethernet adapter ports a 2-4 ports, 1 Gb and/or 10 Gb
depending on PCIe adapter selected
2-4 ports, 1 Gb and/or 10 Gb
depending on PCIe adapter selected
2-4 ports, 1 Gb and/or 10 Gb
depending on PCIe adapter selected
SAS bays in system unit
2.5-inch (disk/SSD) 8 SFF-3 8 SFF-3 8 SFF-3
1.8-inch (SSD) 4 4 4
Media bays
DVD-RAM slimline 1 1 1
HH for tape N/A N/A N/A
Integrated SAS storage controllers
for disk/SSD/DVD
Y Y Y
Dual non-split backplane Dual IOA (zero write cache) Dual IOA (zero write cache) Dual IOA (zero write cache)
Split backplane 2 (zero write cache) 2 (zero write cache) 2 (zero write cache)
Write cache backplane Dual IOA (7.2 GB write cache) Dual IOA (7.2 GB write cache) Dual IOA (7.2 GB write cache)
Easy Tier function Y with any backplane Y with any backplane Y with any backplane
Optional EXP24S ports N N N
PCIe Gen3 adapter slots 7 9 11
PCIe x8 3 3 3
PCIe x16 4 6 8
Max PCIe bus speed (GHz) 8.0 (Gen3) 8.0 (Gen3) 8.0 (Gen3)
Max I/O bandwidth 192 GB/sec 256 GB/sec 320 GB/sec
Service indicator LEDs Y Y Y
Storage backplane notes: Integrated SAS controllers are based on latest IBM patented SAS RAID adapter technology. All backplane options
offer RAID 0, 1, 5, 6, 10 capabilities plus hot spare capability plus Easy Tier function assuming enough drives are physically installed to do so.
Write cache is mirrored for protection and physically is two 1.8 GB DRAM caches offering up to 7.2 GB effective capacity with compression.
14. IBM Power Systems
14
System Node and System Control Unit Details (Power Enterprise Servers )
Power E870/E880
System Unit Details
Power E870 system
node
Power E880 system
node
System control unit
(one per system)
POWER8 SCM sockets 4 4 N/A
Number of SCMs 4 4 N/A
Memory CDIMM slots 32 32 N/A
Max sustained memory
bandwidth to L4 cache from
SCM
230 GB/sec per
socket, 920 G/sec
per node
230 GB/sec per
socket, 920 G/sec
per nod
N/A
Max peak memory bandwidth
to DIMMs from L4 cache
410 GB/sec GB/sec
per socket, 1640
GB/sec per socket
410 GB/sec GB/sec
per socket, 1640
GB/sec per socket
N/A
Integrated ports
System/serial (RJ45) N/A N/A N/A
USB ports N/A N/A N/A
HMC ports (RJ45) 0 0 4
Ethernet adapter ports a
N/A N/A N/A
SAS bays in unit
2.5-inch (disk/SSD) N/A N/A N/A
1.8-inch (SSD) N/A N/A N/A
Media bays
DVD-RAM slimline 0 0 1
Integrated SAS storage
controllers for disk/SSD/DVD
N/A N/A N/A
PCIe Gen3 adapter slots 8 8 N/A
PCIe x8 0 0 N/A
PCIe x16 8 8 N/A
Max PCIe bus speed (GHz) 8.0 (Gen3) 8.0 (Gen3) N/A
Max I/O bandwidth (peak) 256 GB/sec 256 GB/sec N/A
Service indicator LEDs Y Y Y
Operator panel N/A N/A 1
15. IBM Power Systems
15
Server I/O Drawers
Drawer Server
Attachment
PCIe Slots per
Drawer
SAS Bays per
Drawer
Available to
order
Drawer
Footprint
EXP24S (#5887 /
#EL1S)
via SAS 0 24 SFF-2 SAS Y 19” rack 2U
PCIe Gen3 I/O Drawer
(#EMX0 / ELMX)
via x16 PCIe slot 6 or 12 N/A Y 19” rack 4U
Server I/O Drawer Attachment
Server
Drawer
Power
S812L
-
-
Power
S822
Power
S822L
Power
S814
4-core
Power
S814
6/8-core
Power
S824
Power
S824L
Power
E850
Power
E870
Power
E880
EXP24S Max 28 Max 28 n/a Max 28 Max 28 Max 28 p
Max 64 Max 128 Max 168
PCIe Max ½ Max 1 n/a Max 1 Max 2 Max 2p
Max 4 Max 8 Max 16
EXP24S notes:
A Power S812L, S814, S822L, S824, S824L Scale-out server has a maximum of 14 EXP24S if only a system unit is
used. The maximum of 28 requires one or more PCIe Gen3 I/O Drawer to be present.
A Power E850 has a maximum of 16 EXP24S if only a system unit is used. To support the maximum of 64 EXP24S
I/O drawers, three or four PCIe Gen3 drawers are needed.
A single system node Power E870/E880 with 4 PCIe drawers has a maximum of 64 EXP24S drawers. A two-node
Power E870/E880 with 8 PCIe drawers has a max of 128 EXP24S drawers. A three or four node Power E880 has a
max of 168 EXP24S drawers. PCIe Gen3 drawers are required to attain this maximum.
EXP24S is not supported on the S812LC or S822LC models.
A maximum of 16 EXP24S can be attached to one PCIe Gen3 I/O drawer due to cable management considerations
PCIe Gen3 I/O Expansion Drawer notes
PCIe Gen3 I/O drawer is not supported on the S812LC or S822LC models.
Each I/O drawer holds one or two 6-slot fan-out modules. A drawer with just one fan-out module is labeled “½” in
this document. Each fan-out module is attached to a x16 PCIe slot in the Scale-out system unit or in the Enterprise
system node or CEC.
The attachment card in a 4U POWER8 server or in a 5U E870 or E880 Enterprise system node uses one PCIe slot.
The attachment card in a 2U Scale-out server is a double-wide card using two PCIe slots.
Each fan-out module provides 6 PCIe Gen3 slots. Two of the six slots are x16 and four are x8.
Up to four drawers on an E850 and up to four drawers per each system node of an E870/E880 system
PCIe Gen3 I/O drawers can not be shared between two servers
For good cable management practices, a maximum of 4 PCIe Gen3 I/O drawers per 7014-T42/T00 rack is generally
recommended for configurations using a large number of 4-port PCIe adapters with cables attached to all the ports. If
the rack has an 8-inch rear extender making it deeper and able to manage more cables, then a maximum of 6 PCIe
Gen3 I/O drawers is recommended.
Peak I/O bandwidth per fan-out module is 32 GB/sec.
For additional connectivity information, please reference the IBM Sales Manual for more information on I/O features and adapters.
16. IBM Power Systems
16
Physical Planning Characteristics
Note: More comprehensive information may be found in the IBM Site and Hardware Planning document at
http://www.ibm.com/support/knowledgecenter/POWER8/p8hdx/POWER8welcome.htm . Plus, additional summary information
can be found in the IBM Sales Manual for each server at ibm.com/common/ssi .
Server
Power S812LC
Power S822LC
8335-GTA
Power S822LC
8335-GCA
Packaging 19" rack drawer
(2U)
19" rack drawer
(2U)
19" rack drawer
(2U)
Power supplies
used
Two 1000 or1200W
N + 1 standard
Two 1300W
N+1 standard
Two 1300W
N+1 standard
Voltage (AC)
single phase
100 -120 or
200 - 240
200 – 240 200 - 240
Maximum altitude
Feet 10000 10000 10000
Meters 3048 3048 3048
Server
Power S812L
Power S822
Power S822L
Power S814
(rack)
Power S814
(tower)
Power S824
Power S824L
Packaging 19" rack drawer
(2U)
19" rack drawer
(2U)
19" rack drawer
(4U)
Tower 19" rack drawer
(4U)
Power supplies
used
Two 900 W
N + 1 standard
Two 1400 W
N+1 standard
Two 1400 W
N+1 standard
Two 900 W
N+1 standard
Four 900 W
N+1 standard
Voltage (AC)
single phase
100 -120 or
200 - 240
200 – 240
100-120 or
200 - 240
100-120 or
200-240
100 – 120 or
200 - 240
Maximum altitude
Feet 10000 10000 10000 10000 10000
Meters 3048 3048 3048 3048 3048
Server
Power E850
Power E870 / E880
System node
Power E870 / E880
System control unit
Packaging 19" rack drawer
4U
19" rack drawer
5U per node
19" rack drawer (one per 870/880)
2U
Power supplies
used
Four 1400 W
N + 1 standard
Four 1720 W per node
N + 1 standard
Zero – redundant power input from
system node(s)
Voltage (AC)
single phase
200 - 240 200 - 240 n/a
Maximum altitude
Feet 10000 10000 10000
Meters 3050 3048 3048
Note: As an alternative to AC power supplies, HVDC power supplies are available for the S812L, S822, S822L, S814, S824, S824L, E850,
E870 and E880 and for the PCIe Gen3 I/O drawer. HVDC power supplies are not announced for the HMC or EXP24S I/O Drawer.
Racks 7014-S25 or #0555 7014-T00 or #0551 7014-T42 or #0553 7014-B42 7965-94Y
Slim Rack
25U 36U 42U 42U 42U
Height
Inches 49.0 71.0 – 75.8 79.3 79.3 78.8
Millimeters 1344 1804 – 1926 2015 2015 2002
Width (can vary depending on use of side panels)
Inches 23.8 24.5 – 25.4 24.5 - 25.4 24.5 - 25.4 23.6
Millimeters 605 623 – 644 623 – 644 623 - 644 600
Depth (can vary depending on door options selected)
o Inches 39.4 41.0 – 45.2 41.0 - 45.2 41.0 - 55.5 43.1 – 48.2
o Millimeters 1001 1042 – 1098 1043 – 1098 1042 - 1409 1095 - 1224
Power E870 and E880 are supported by IBM Manufacturing only in the 7014-T42 or #0553.
17. IBM Power Systems
17
Warranty1 / Installation
Warranty Service Levels
Power S812LC
Power S822LC
Power S812L
Power S822
Power S822L
Power S814
Power S824
Power S824L
24x7 with two hour service
objective2 Optional Optional Optional Optional Optional
24x7 with four hour service
objective
Optional Optional Optional Optional Optional
9x5 with four hour service
objective
Optional Optional Optional Optional Optional
9x5 next-business-day Standard 6
Standard 3
Standard 3
Standard 3
Standard 3
Warranty Period 3 years 3 years 3 years 3 years 3 years
Server install 4
CSU CSU CSU CSU CSU
Warranty Service Levels Power E850 Power E870 Power E880
24x7 with two hour service
objective2 Optional Optional Optional
24x7 with four hour service
objective Included* Standard Standard
9x5 with four hour service
objective - - -
9x5 next-business-day
Standard - -
Warranty Services Period
3 / 1 years 5
1 year 1 year
Server installation 4
CSU IBI IBI
1. These warranty terms and conditions are for the United States and may be different in other countries. Consult your local IBM
representative or IBM Business Partner for country-specific information.
2. Available in selected cities.
3. Mandatory Customer Replaceable Unit (CRU) or Limited On-site service depending on the feature code. With an upgrade
to a higher support service level, the mandatory CRU features become optional CRU.
4. CSU = Customer Set Up, IBI = Installation by IBM For server hardware only. Note for IBI severs, server feature
codes such as an EXP24S I/O drawer or PCIe Gen3 I/O drawer or PCIe adapter or disk drive are installed by the IBM service
representative as part of the normal warranty/maintenance coverage. Optionally a client may choose to install CSU features
without an IBM service representative.
5. System is provided with a one year standard warranty 9x5 NBD. For your convenience, IBM has provided an upgrade to 24x7
coverage PLUS two additional years of extended warranty services (varies by country).
6. Mandatory Customer Replaceable Unit (CRU). With an upgrade to a higher support service level, mandatory CRU
becomes optional CRU.
18. IBM Power Systems
18
Power S LC Class Servers Software Support
Power Systems Software Power
S812LC
Power S822LC
8335-GTA
Power S822LC
8335-GCA
Software Tier Small Small Small
PowerVM™
PowerVM Linux Edition N/A N/A N/A
PowerVM Standard and Enterprise Editions N/A N/A N/A
PowerKVM 3.1 Supported N/A Supported
AIX
AIX N/A N/A N/A
IBM i
IBM i N/A N/A N/A
Linux
Red Hat Enterprise
Linux 6.6 and 7.1 ( BE )
Supported Supported Supported
Red Hat Enterprise
Linux 7.2 ( BE and LE )
Supported Supported Supported
SUSE Linux Enterprise Server 11 (BE) Supported Supported Supported
SUSE Linux Enterprise Server 12 * (LE) Supported Supported Supported
Ubuntu 14.04 (LE) Supported Supported Supported
PowerHA™
PowerHA SystemMirror for AIX Standard and
Enterprise Editions
N/A N/A N/A
PowerHA SystemMirror for i N/A N/A N/A
* Or later version
19. IBM Power Systems
19
Power S Class Servers Software Support
Power Systems Software
Power S812L Power S822 Power S822L Power S814
Power
S824
Power
S824L
Software Tier Small Small Small Small Small Small
PowerVM™ N/A
PowerVM Linux Edition Supported N/A Supported N/A N/A Supported 4
PowerVM Standard and Enterprise Editions N/A Supported N/A Supported Supported N/A
PowerKVM Supported N/A Supported N/A N/A Supported4
AIX
AIX 6.1 * N/A Supported N/A Supported Supported N/A
AIX 7.1 * N/A Supported N/A Supported Supported N/A
IBM i
IBM i Software Tier N/A Small P10 3,5
N/A
Small
4-core: P05 3
6/8-core: P10 3
Small P20 3
N/A
IBM i 7.1 TR8 * N/A Supported s
N/A Supported Supported N/A
IBM i 7.2 * N/A Supported s
N/A Supported Supported N/A
Linux
Red Hat Enterprise
Linux 6.6 *(BE)
Supported Supported Supported Supported Supported Supported4
Red Hat Enterprise
Linux 7.1(LE and BE)
Supported Supported Supported Supported Supported Supported4
RedHat Enterprise Linux 7.2(LE and BE) Supported N/A Supported N/A Supported N/A
SUSE Linux Enterprise Server 11 (BE)
12(LE)
Supported Supported Supported Supported Supported Supported4
Ubuntu 14.04 (LE) Supported N/A Supported N/A N/A Supported,
PowerHA™
PowerHA SystemMirror for AIX 6.12
Standard
and Enterprise Editions
N/A Supported N/A Supported Supported N/A
PowerHA SystemMirror for AIX 72
Standard
Edition
N/A Supported N/A Supported Supported N/A
PowerHA SystemMirror for IBM i Version7
Standard and Enterprise Editions
N/A Supported N/A Supported Supported N/A
* Or later version
1 – Note that AIX 6.1 and AIX 7.1 Express Edition may be used for partitions of up to 4 cores and 8 GB of memory per core.
2 – PowerHA SystemMirror for AIX 6.1 is supported on AIX 5.3,AIX 6.1 and AIX 7.1. PowerHA SystemMirror for AIX 7 is supported with both AIX
6.1 and AIX 7.1
3 – P05 and P10 requires user entitlements and includes 5250 Enterprise Enablement capability. P20 does not have user entitlements and
5250 Enterprise Enablement is ordered as an optional hardware feature code.
4. When no GPU installed
5. There is a maximum of two cores per IBM i partition on a S822 server. Multiple IBM i partitions on a server are supported. IBM i 7.1 TR11
or 7.2 TR3 or later is required. Also note all I/O is virtualized through VIOS, there is no “native” non-VIOS I/O.
20. IBM Power Systems
20
Power Enterprise Servers Software Support
Power Systems Software Power E850 Power E870 Power E880
Software Tier Small Medium Medium
PowerVM™
PowerVM Linux Edition With Power IFL With Power IFL With Power IFL
PowerVM Standard Edition Supported N/A N/A
PowerVM Enterprise Editions Supported Standard Standard
PowerKVM N/A N/A N/A
AIX
AIX 6.1 TL9 * (TL8 Jan 2015)
With TL9 *
TL8 Sept 2015
Supported Supported
AIX 7.1 TL3 * (TL2 Jan 2015)
With TL3 *
TL2 Sept 2015
Supported Supported
AIX 6.1 TL8 * with virtual I/O only With TL8 * Supported Supported
AIX 7.1 TL2 * with virtual I/O only With TL2 * Supported Supported
IBM i
IBM i Software Tier N/A P30 P30
IBM i 7.1 TR9 * N/A Supported Supported
IBM i 7.2 TR1 * N/A Supported Supported
Linux
Red Hat Enterprise
Linux 6.6(BE) 7.1(BE,LE)
Supported Supported Supported
SUSE Linux Enterprise Server 11(BE) 12(LE) Supported Supported Supported
Ubuntu 14.04(LE) Supported Supported Supported
PowerHA™
PowerHA SystemMirror for AIX 6.12
Standard
and Enterprise Editions
Supported Supported Supported
PowerHA SystemMirror for AIX 72
Standard
Edition
Supported Supported Supported
PowerHA SystemMirror for IBM i Version 7
Standard and Enterprise Editions
N/A Supported Supported
* Or later version
** IBM i 7.1 TR10 and IBM iI 7.2 TR2 are required for 4-node or 4 PCIe I/O drawer per node configurations
21. IBM Power Systems
21
Performance Notes
The performance information contained herein is current as of the date of this document. All performance
benchmark values and estimates are provided “AS IS” and no warranties or guarantees are expressed or implied
by IBM. Buyers should consult other sources of information, including system benchmarks, to evaluate the
performance of a system they are considering.
rPerf (Relative Performance) is an estimate of commercial processing performance relative to other IBM UNIX®
systems. It is derived from an IBM analytical model which uses characteristics from IBM internal workloads, TPC
and SPEC benchmarks. The rPerf model is not intended to represent any specific public benchmark results and
should not be reasonably used in that way. The model simulates some of the system operations such as CPU,
cache and memory. However, the model does not simulate disk or network I/O operations.
rPerf estimates are calculated based on systems with the latest levels of AIX and other pertinent software at the
time of system announcement. Actual performance will vary based on application and configuration specifics. The
IBM eServer™ pSeries® 640 is the baseline reference system and has a value of 1.0. Although rPerf may be used
to approximate relative IBM UNIX commercial processing performance, actual system performance may vary and
is dependent upon many factors including system hardware configuration and software design and configuration.
Variations in incremental system performance may be observed in commercial workloads due to changes in the
underlying system architecture. For additional information about rPerf, contact your local IBM office or an
IBM authorized reseller.
Commercial Processing Workload (CPW) is a relative measure of performance of systems
running the IBM i operating system. Performance in client environments may vary. The value is
based on maximum configurations. For a complete description Please refer to the “IBM Power
Systems Performance Capabilities Reference - IBM i operating system” at the following Web
site of CPW and the CPW rating for IBM Power Systems:
www.ibm.com/systems/power/software/i/management/performance/resources.html
All performance estimates are provided “AS IS” and no warranties or guarantees are expressed or implied by IBM.
Buyers should consult other sources of information, including system benchmarks and application sizing guides to
evaluate the performance of a system they are considering buying. Actual system performance may vary and is
dependent upon many factors including system hardware configuration and software design and configuration.
IBM recommends application-oriented testing for performance predictions. Additional information about the
performance benchmarks, values and systems tested is available from your IBM marketing representative or
IBM Authorized Reseller or access the following on the Web:
SPEC – http://www.spec.org
TPC – http://www.tpc.org
More information
Contact your IBM sales representative or IBM Business Partner
Access the Power Systems Products and Services page on IBM’s World Wide Web server at
ibm.com/systems/power and then select the appropriate hardware or software option
Product announcement letters and Sales Manual containing more details on hardware and software offerings
are available at ibm.com/common/ssi
More detailed benchmark and performance information is available at
ibm.com/systems/p/hardware/benchmarks , ibm.com/systems/p/hardware/system_perf.html and at
ibm.com/systems/i/solutions/perfmgmt/resource.html .